Author

Yi-Feng Zhang

h-index 0 View on Semantic Scholar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Aug 2026

Janus: Realizing Practical Operator Parallelism for Latency-Sensitive DNN Inference on GPUs

Janus is proposed, a novel resource- and latency-aware operator scheduling framework to enable efficient and practical operator parallelism for DNN inference on GPUs and introduces an effective stream allocation mechanism that fully incorporates operator resource constraints and latency heterogeneity.

Yi-Feng Zhang, Hao-Xuan Ma, Yu-Xing Long et al. · ACM Transactions on Architec... · 0 citations

Preprint Sep 2026

Latency-Aware Orchestration for Multi-Agent LLM Workflows on Heterogeneous GPUs

Concurrent multi-agent workflows expose future dependencies and serving-state requirements while running on heterogeneous GPU pools with time-varying load, model residency, and resource availability. The logical workflow defines the required computation, whereas its physical scheduling units, model-lifecycle actions, r...

Jing-Hao Wang, Yi-Feng Zhang, Xiao Zhou et al. · 0 citations

Open access Aug 2026

Janus: Realizing Practical Operator Parallelism for Latency-Sensitive DNN Inference on GPUs

With the growing deployment of Deep Neural Networks (DNNs) in latency-critical services, optimizing inference efficiency on GPUs has become crucial. While exploiting operator parallelism offers a promising avenue to accelerate inference and improve hardware utilization, existing approaches often overlook two critical f...

Yifeng Zhang, Haoxuan Ma, Yuxing Long et al. · ACM Transactions on Architec... · 0 citations